Search Results for author:
Found 2 papers, 2 papers with code
Megapixel Image Generation with Step-Unrolled Denoising Autoencoders
An ongoing trend in generative modelling research has been to push sample resolutions higher whilst simultaneously reducing computational requirements for training and sampling.
Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations
Measures specifically designed to take into account the binaural properties of the signal are often intrusive - characterised by requiring access to a clean speech signal - and typically rely on combining both channels into a single-channel signal before making predictions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
